Yi Tu
Scholar

Yi Tu

Google Scholar ID: 5yO-6j8AAAAJ
Ant Group
Computer VisionDocument UnderstandingVision Language Model
Google Scholar↗
Citations & Impact
All-time
Citations
1,011
 
H-index
8
 
i10-index
8
 
Publications
15
 
Co-authors
4
list available
Contact
No contact links provided.
Publications
10 items
SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding
2026
Cited
0
Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs
2026
Cited
0
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
2025
Cited
0
Metaphor-based Jailbreaking Attacks on Text-to-Image Models
2025
Cited
0
SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
2025
Cited
0
Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models
2025
Cited
0
Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting
2025
Cited
0
Metaphor-based Jailbreaking Attacks on Text-to-Image Models
2025
Cited
0
Resume (English only)
Co-authors
4 total
Co-author 1
Co-author 1
Dawei Cheng
Dawei Cheng
Tongji University
Li Niu
Li Niu
Shanghai Jiao Tong University
Chong Zhang
Chong Zhang
MiroMind AI; Fudan University